% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Stecconi:909568,
author = {Stecconi, Tommaso and Guido, Roberto and Berchialla, Luca
and La Porta, Antonio and Weiss, Jonas and Popoff, Youri and
Halter, Mattia and Sousa, Marilyne and Horst, Folkert and
Dávila, Diana and Drechsler, Ute and Dittmann, Regina and
Offrein, Bert Jan and Bragaglia, Valeria},
title = {{F}ilamentary {T}a{O} x /{H}f{O} 2 {R}e{RAM} {D}evices for
{N}eural {N}etworks {T}raining with {A}nalog {I}n‐{M}emory
{C}omputing},
journal = {Advanced electronic materials},
volume = {8},
number = {10},
issn = {2199-160X},
address = {Weinheim},
publisher = {Wiley-VCH Verlag GmbH $\&$ Co. KG},
reportid = {FZJ-2022-03250},
pages = {2200448 -},
year = {2022},
abstract = {The in-memory computing paradigm aims at overcoming the
intrinsic inefficiencies of Von-Neumann computers by
reducing the data-transport per arithmetic operation.
Crossbar arrays of multilevel memristive devices enable
efficient calculations of matrix-vector-multiplications, an
operation extensively called on in artificial intelligence
(AI) tasks. Resistive random-access memories (ReRAMs) are
promising candidate devices for such applications. However,
they generally exhibit large stochasticity and
device-to-device variability. The integration of a
sub-stoichiometric metal-oxide within the ReRAM stack can
improve the resistive switching graduality and
stochasticity. To this purpose, a conductive TaOx layer is
developed and stacked on HfO2 between TiN electrodes, to
create a complementary metal-oxide-semiconductor-compatible
ReRAM structure. This device shows accumulative conductance
updates in both directions, as required for training neural
networks. Moreover, by reducing the TaOx thickness and by
increasing its resistivity, the device resistive states
increase, as required for reduced power consumption. An
electric field-driven TaOx oxidation/reduction is
responsible for the ReRAM switching. To demonstrate the
potential of the optimized TaOx/HfO2 devices, the training
of a fully-connected neural network on the Modified National
Institute of Standards and Technology database dataset is
simulated and benchmarked against a full precision digital
implementation.},
cin = {PGI-7 / JARA-FIT},
ddc = {621.3},
cid = {I:(DE-Juel1)PGI-7-20110106 / $I:(DE-82)080009_20140620$},
pnm = {5233 - Memristive Materials and Devices (POF4-523) / MANIC
- Materials for Neuromorphic Circuits (861153) / DFG project
167917811 - SFB 917: Resistiv schaltende Chalkogenide für
zukünftige Elektronikanwendungen: Struktur, Kinetik und
Bauelementskalierung "Nanoswitches" (167917811) /
BMBF-16ME0398K - Verbundprojekt: Neuro-inspirierte
Technologien der künstlichen Intelligenz für die
Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K) /
BMBF-16ME0404 - Verbundprojekt: Neuro-inspirierte
Technologien der künstlichen Intelligenz für die
Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0404) /
BMBF-03ZU1106AB - NeuroSys: "Memristor Crossbar
Architekturen (Projekt A) - B" (BMBF-03ZU1106AB) / ACA -
Advanced Computing Architectures (SO-092)},
pid = {G:(DE-HGF)POF4-5233 / G:(EU-Grant)861153 /
G:(GEPRIS)167917811 / G:(DE-82)BMBF-16ME0398K /
G:(DE-82)BMBF-16ME0404 / G:(DE-Juel1)BMBF-03ZU1106AB /
G:(DE-HGF)SO-092},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000822534500001},
doi = {10.1002/aelm.202200448},
url = {https://juser.fz-juelich.de/record/909568},
}